Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely new context beyond the annotations: the paid-plan prerequisite, which affects whether the call is even permitted. It stops short of disclosing cost/rate behavior or whether results are cached/fresh.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the first front-loads the verb and the exact contents of the summary, the second carries the two operational constraints. No filler and nothing buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema and annotations exist, so return shapes and safety need not be restated. Purpose, platform filtering, and the plan gate are all present; the only material omission is any explanation of the windowDays parameter, which leaves the agent guessing about the aggregation window.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description has to carry both parameters. It covers platform ('Optionally filter by platform') but never mentions windowDays, and the phrase 'next 7 days' refers to token expiry rather than that parameter's 7/30/90 enum with a default of 30 — so half the parameters remain semantically unclarified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb (get) plus well-defined resource (account-health summary) with an enumerated payload: connected-account counts, scheduled/published/failed post counts, draft count, and expiring tokens. This is clearly distinguishable from siblings like get_channel_analytics and list_connected_accounts, which return different scopes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

States two usable conditions: the output can be narrowed with an optional platform filter, and the tool requires a paid plan, which is a real gating prerequisite. It does not, however, contrast itself with near-neighbors such as get_channel_analytics or get_plan_limits, so the agent must infer when this summary is preferred over those.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.